abgulati/LARS
An application for running LLMs locally on your device, with your documents, facilitating detailed citations in generated responses.
Built on pure llama.cpp with no framework abstractions, LARS supports 12+ embedding models and multiple OCR backends (local, Azure Computer Vision, Azure Document Intelligence) for flexible text extraction across 10+ file formats. The architecture enables dynamic LLM swapping, GPU-accelerated CUDA inference, and granular parameter tuning—all via a web UI with integrated document reader for viewing cited sources directly within response windows.
631 stars. No commits in the last 6 months.
Stars
631
Forks
61
Language
Python
License
AGPL-3.0
Category
Last pushed
Oct 29, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/abgulati/LARS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LearningCircuit/local-deep-research
Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports...
NVIDIA-AI-Blueprints/rag
This NVIDIA RAG blueprint serves as a reference solution for a foundational Retrieval Augmented...
hienhayho/rag-colls
Collection of recent advanced RAG techniques.
jeremiahbohr/literature-mapper
Transform academic PDFs into a Knowledge Graph with typed claims, temporal analysis,...
Denis2054/RAG-Driven-Generative-AI
This repository provides programs to build Retrieval Augmented Generation (RAG) code for...